Lab 5

---

title: “Lab 5” author: “R4L” date: “2/13/2019” output: html_document —

Team

team_milk <- milk %>%
  filter(state %in% c("Texas", "Colorado", "California", "Tennessee", "Illinois"))  

Plot

Individual

Yen-Ting Shen

milk1996 <- milk %>%
  filter(year == 1996)

ggplot(data= milk1996, aes(milk_million, fill = region), position = "fill")+
  geom_histogram(bins = 15)+
  ggtitle('Histogram of milk produced in 1996 by state')

milk1996 %>%
  summarise(avg_milk_produced = mean(milk_million), median_milk_produced = median(milk_million))%>%
  arrange(desc(avg_milk_produced))

##   avg_milk_produced median_milk_produced
## 1           3080.12                 1480

team_milk$average <- national$milk 

ggplot(data = team_milk, aes(x = year, y = milk_million, color =state))+
  geom_point()+
  geom_smooth(aes(x = year, y = average), se = FALSE)

## `geom_smooth()` using method = 'loess' and formula 'y ~ x'

The year when the most milk was produced in the United States.

The year when the most milk produced was in 2017 with production 4309.32 million lb.

arrange(national, milk) %>%
  top_n(1)

## Selecting by milk

## # A tibble: 1 x 2
##    year  milk
##   <dbl> <dbl>
## 1  2017 4309.

The year when the least milk was produced in the United States.

The year when the least milk produced was in 1975 with production 2307.96 million lb.

arrange(milk1996, desc(milk_million))%>%
  top_n(1)

## Selecting by milk_million

##    region      state year milk_produced milk_million
## 1 Pacific California 1996    2.5848e+10        25848

descmilkyen <- milk1996 %>%
  mutate(milkrank = -milk_million) %>%
  arrange(-milk_million) 

top_n(descmilkyen,1)%>%
  select(region, state, year, milk_produced, milk_million)

## Selecting by milkrank

##    region  state year milk_produced milk_million
## 1 Pacific Alaska 1996       1.4e+07           14

Emery Schattinger

milk1998 <- milk %>%
  filter(year == 1998) 

ggplot(data = milk1998, aes(x = as.factor(year), y = milk_million, fill = region)) +
  geom_boxplot() + 
  ggtitle('Pounds of Milk Produced in 1998 by Region') + 
  scale_fill_discrete(name = 'Region') + 
  xlab('Year') +
  ylab('Milk Produced (Millions lb)')

descnational <- national %>%
  mutate(avg = -milk) %>%
  arrange(-milk) 


top_n(descnational,1)%>%
  select(year, milk)

## Selecting by avg

## # A tibble: 1 x 2
##    year  milk
##   <dbl> <dbl>
## 1  1975 2308.

milk1998 %>%
  filter(year == 1998) %>%
  summarise(avg_milk_produced = mean(milk_million), 
            median_milk_produced = median(milk_million))%>%
  arrange(desc(avg_milk_produced)) 

##   avg_milk_produced median_milk_produced
## 1           3145.22               1411.5

arrange(milk1998, desc(milk_million))%>%
  top_n(1)

## Selecting by milk_million

##    region      state year milk_produced milk_million
## 1 Pacific California 1998     2.762e+10        27620

leastmilk <- milk1998 %>%
  mutate(milkrank = -milk_million) %>%
  arrange(-milk_million) 

top_n(leastmilk,1)%>%
  select(region, state, year, milk_produced, milk_million)

## Selecting by milkrank

##    region  state year milk_produced milk_million
## 1 Pacific Alaska 1998       1.4e+07           14

In 2017, report the 5 states that produced the most milk.

The 5 states that produced the most milk in 2017 was California with production 397,798 million lb.

filter(team_milk, year == 2017) %>%
  arrange(desc(milk_million))

##            region      state year milk_produced milk_million average
## 1         Pacific California 2017    3.9798e+10        39798 4309.32
## 2 Southern Plains      Texas 2017    1.2054e+10        12054 4171.94
## 3        Mountain   Colorado 2017    4.1890e+09         4189 4248.12
## 4       Corn Belt   Illinois 2017    1.9290e+09         1929 4024.60
## 5     Appalachian  Tennessee 2017    6.9300e+08          693 4121.12

In 2017, report the 5 states that produced the least milk.

The 5 states that produced the least milk in 2017 was Tennessee with production 693 million lb.

filter(team_milk, year == 2017) %>%
  arrange(milk_million)

##            region      state year milk_produced milk_million average
## 1     Appalachian  Tennessee 2017    6.9300e+08          693 4121.12
## 2       Corn Belt   Illinois 2017    1.9290e+09         1929 4024.60
## 3        Mountain   Colorado 2017    4.1890e+09         4189 4248.12
## 4 Southern Plains      Texas 2017    1.2054e+10        12054 4171.94
## 5         Pacific California 2017    3.9798e+10        39798 4309.32

Individual

Yen-Ting Shen

milk1998<- milk%>%
  
  filter(year==1998)

ggplot(data = milk1998)+
  
  geom_point(aes(x=state, y=milk_million,color=region))+
  
  theme(legend.position = "bottom")+
  
  theme(axis.text.x = element_text(angle = 90, hjust = 0.5, vjust = 0.5))

  ggtitle('Milk Produced in 1998')

## $title
## [1] "Milk Produced in 1998"
## 
## attr(,"class")
## [1] "labels"

Average Milk Produced in 1998

milk1998%>%
  
summarise(Average_Milk_Produced_1998=mean(milk_million))

##   Average_Milk_Produced_1998
## 1                    3145.22

Median of Milk Produced in 1998

milk1998%>%
  
summarise(Median_of_Milk_Produced_1998=median(milk_million))

##   Median_of_Milk_Produced_1998
## 1                       1411.5

ggplot(data= milk1996, aes(milk_million, fill = region), position = "fill")+
  geom_histogram(bins = 15)+
  ggtitle('Histogram of milk produced in 1996 by state')+
  xlab('Milk Produced (Millions lb)')

#### Report

The average milk produced in 1996 was 3080.12 million lb, and the median was 1480 million lb.

milk1996 %>%
  summarise(avg_milk_produced = mean(milk_million), median_milk_produced = median(milk_million))%>%
  arrange(desc(avg_milk_produced))

##   avg_milk_produced median_milk_produced
## 1           3080.12                 1480

The state that produced the most milk in 1996 was California, which they produced 25,848 million lb.

arrange(milk1996, desc(milk_million))%>%
  top_n(1)

## Selecting by milk_million

##    region      state year milk_produced milk_million
## 1 Pacific California 1996    2.5848e+10        25848

The state that produced the least milk in 1996 was Alaska, which they produces 14 million lb.

descmilkyen <- milk1996 %>%
  mutate(milkrank = -milk_million) %>%
  arrange(-milk_million) 

Emery Schattinger

milk1998 <- milk %>%
  filter(year == 1998) 

ggplot(data = milk1998, aes(x = as.factor(year), y = milk_million, fill = region)) +  geom_boxplot() + 
  ggtitle('Pounds of Milk Produced in 1998 by Region') + 
  scale_fill_discrete(name = 'Region') + 
  xlab('Year') +
  ylab('Milk Produced (Millions lb)')

Report

milk1998 %>%
  filter(year == 1998) %>%
  summarise(avg_milk_produced = mean(milk_million), 
            median_milk_produced = median(milk_million))%>%
  arrange(desc(avg_milk_produced)) 

##   avg_milk_produced median_milk_produced
## 1           3145.22               1411.5

arrange(milk1998, desc(milk_million))%>%
  top_n(1)

## Selecting by milk_million

##    region      state year milk_produced milk_million
## 1 Pacific California 1998     2.762e+10        27620

leastmilk <- milk1998 %>%
  mutate(milkrank = -milk_million) %>%
  arrange(-milk_million) 

top_n(leastmilk,1)%>%
  select(region, state, year, milk_produced, milk_million)

## Selecting by milkrank

##    region  state year milk_produced milk_million
## 1 Pacific Alaska 1998       1.4e+07           14

Jason Giblin

milk1998 <- milk %>%
  filter(year == 1998)

ggplot(data= milk1998, aes(milk_million, fill = region), position = "fill")+
  geom_histogram(bins = 10)+
  ggtitle('Histogram of milk produced in 1998 by state')

Report

milk1998 %>%
  summarise(avg_milk_produced = mean(milk_million), median_milk_produced = median(milk_million))%>%
  arrange(desc(avg_milk_produced))

##   avg_milk_produced median_milk_produced
## 1           3145.22               1411.5

arrange(milk1998, desc(milk_million)) %>%
   top_n(1)

## Selecting by milk_million

##    region      state year milk_produced milk_million
## 1 Pacific California 1998     2.762e+10        27620

Tiger Su

milk1998<- milk%>%
  
  filter(year==1998)

  ggplot(data = milk1998)+
  
  geom_point(aes(x=state, y=milk_million,color=region))+
  
  theme(legend.position = "bottom")+
  
  theme(axis.text.x = element_text(angle = 90, hjust = 0.5, vjust = 0.5))+
  
  ggtitle('Milk Produced in 1998')+
  
  xlab('States')+

  ylab('Milk in Million Gallons')

Report

Average Milk Produced in 1998

milk1998%>%
  
summarise(Average_Milk_Produced_1998=mean(milk_million))

##   Average_Milk_Produced_1998
## 1                    3145.22

Median of Milk Produced in 1998

milk1998%>%
  
summarise(Median_of_Milk_Produced_1998=median(milk_million))

##   Median_of_Milk_Produced_1998
## 1                       1411.5

Most Milk Produced State in 1998

milk1998%>%
  
arrange(desc(milk_million))%>%
  
  slice(1)

##    region      state year milk_produced milk_million
## 1 Pacific California 1998     2.762e+10        27620

Lest Milk Produced State in 1998

milk1998%>%
  
arrange(milk_million)%>%
  
  slice(1)

##    region  state year milk_produced milk_million
## 1 Pacific Alaska 1998       1.4e+07           14